Using Chinda LLM 4B with OpenWebUI - Complete User Guide
🎯 Introduction
Chinda LLM 4B is an open-source Thai language model developed by the iApp Technology team, capable of thinking and responding in Thai with high accuracy using the latest Qwen3-4B architecture.
OpenWebUI is a beautiful, user-friendly web interface for Ollama that provides ChatGPT-like experience for local AI models. It offers an intuitive chat interface with features like conversation history, model management, and customizable settings.
The latest version of OpenWebUI (v0.6.13) includes exciting new features such as Azure OpenAI embedding support, smarter custom parameter handling, general backend refactoring, and improved localization for multiple languages.
🚀 Step 1: Installing Docker
Install Docker
If you don't have Docker installed:
- Windows/Mac: Download from https://www.docker.com/products/docker-desktop
- Linux: Follow your distribution's Docker installation guide
GPU Support Setup (Optional but Recommended)
For NVIDIA GPUs:
Install NVIDIA Container Toolkit to enable GPU acceleration:
Ubuntu/Debian:
# Add NVIDIA package repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
# Install nvidia-container-toolkit
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
sudo systemctl restart docker
For other Linux distributions, macOS, or Windows: Follow the NVIDIA Container Toolkit installation guide
📱 Step 2: Running OpenWebUI with Integrated Ollama
Method 1: OpenWebUI with Built-in Ollama (Recommended)
This method runs both OpenWebUI and Ollama in a single container setup:
For systems WITHOUT GPU:
docker run -d -p 3000:8080 -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
For systems WITH NVIDIA GPU:
docker run -d -p 3000:8080 --gpus all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
Method 2: Using Docker Compose (Advanced)
Create a docker-compose.yml
file:
version: '3.8'
services:
open-webui:
image: ghcr.io/open-webui/open-webui:ollama
container_name: open-webui
ports:
- "3000:8080"
volumes:
- ollama:/root/.ollama
- open-webui:/app/backend/data
restart: always
# Uncomment the following lines for GPU support
# deploy:
# resources:
# reservations:
# devices:
# - driver: nvidia
# count: all
# capabilities: [gpu]
volumes:
ollama:
open-webui:
Run with:
docker-compose up -d
Access OpenWebUI
- Open your web browser
- Go to
http://localhost:3000
- You should see the OpenWebUI welcome screen
🔍 Step 3: Download Chinda LLM 4B Model
Using OpenWebUI Interface (Recommended)
Once OpenWebUI is running, you can download the Chinda LLM 4B model directly through the web interface:
- Open your browser and go to
http://localhost:3000
- Complete the initial setup (create account)
- Search for the model by typing
iapp/chinda-qwen3-4b
in the model search box
- Click Pull "iapp/chinda-qwen3-4b" from Ollama.com
- Wait for the download to complete (approximately 2.5GB)
- You'll see a success notification when the model is downloaded
Using Docker Exec (Alternative)
You can also download the model using Docker exec:
# Download Chinda LLM 4B model
docker exec -it open-webui ollama pull iapp/chinda-qwen3-4b
# Verify the model is downloaded
docker exec -it open-webui ollama list
🔍 Step 4: Initial Setup
Create Your Account
- On the first visit, you'll see a Sign Up form
- Enter your preferred email and password
- Click Create Account
- You'll be automatically logged in
Note: This is a local account only for your computer - no data is sent to external servers.
⚙️ Step 5: Using Chinda LLM 4B
Select the Model
- In the chat interface, look for the Model dropdown at the top
- Select
chinda-qwen3-4b:latest
from the list - If you don't see it, make sure you've downloaded the model using the steps above
Start Your First Conversation
- Type your message in Thai in the chat box
- Press Enter or click the send button
- Chinda LLM will respond in Thai
Example Conversations:
As you can see in the screenshot above, Chinda LLM responds naturally in Thai and introduces itself as an AI assistant developed by iApp Technology Co., Ltd. The model demonstrates its capability to understand context and provide thoughtful responses in Thai.
Mathematics Question:
You: ช่วยแก้สมการ 3x + 7 = 22 ให้หน่อย
Chinda: ผมจะช่วยแก้สมการ 3x + 7 = 22 ให้คุณครับ
ขั้นตอนการแก้:
1) 3x + 7 = 22
2) 3x = 22 - 7
3) 3x = 15
4) x = 15 ÷ 3
5) x = 5
ดังนั้น x = 5 ครับ
Document Writing:
You: ช่วยเขียนอีเมลขอบคุณลูกค้าให้หน่อย
Chinda: ผมจะช่วยเขียนอีเมลขอบคุณลูกค้าให้คุณครับ
เรื่อง: ขอบพระคุณสำหรับการใช้บริการ
เรียน คุณลูกค้าที่เคารพ,
ทางบริษัทฯ ขอขอบพระคุณอย่างสูงสำหรั บการให้ความไว้วางใจและใช้บริการของเรา...
🎨 Step 6: Advanced Features
Conversation Management
Create New Chats:
- Click the + button to start a new conversation
- Each conversation is saved separately
- You can switch between conversations anytime
Rename Conversations:
- Click on the conversation title
- Enter a new name to organize your chats
Export Conversations:
- Click on the conversation settings (three dots)
- Select Export to save as JSON or Markdown
Customize Model Settings
Access Model Settings:
- Click the Settings icon next to the model name
- Adjust parameters like:
- Temperature (0.1-1.0): Controls creativity
- Top P (0.1-1.0): Controls response diversity
- Top K (1-100): Limits vocabulary choices
- Max Tokens: Maximum response length
Recommended Settings for Chinda LLM:
- Temperature: 0.7 (balanced creativity)
- Top P: 0.9 (good diversity)
- Top K: 40 (focused responses)